【摘要】：隨著計(jì)算機(jī)技術(shù)不斷的發(fā)展,出現(xiàn)了越來(lái)越多的人機(jī)交互方式。由于手勢(shì)的直觀性、自然性等特點(diǎn),所以手勢(shì)識(shí)別也成為了一種重要的人機(jī)交互方式(HCI)。但手勢(shì)自身具有的多樣性,以及在時(shí)空上的差異性等特點(diǎn),使手勢(shì)識(shí)別成為一個(gè)極富挑戰(zhàn)性的多學(xué)科交叉的研究課題。如何能夠快速而準(zhǔn)確的識(shí)別出手勢(shì)所表達(dá)的意義,成為了人們研究的重點(diǎn)。本文以兼顧實(shí)時(shí)性和提高手勢(shì)的識(shí)別率為研究目標(biāo),設(shè)計(jì)實(shí)現(xiàn)一個(gè)基于計(jì)算機(jī)視覺(jué)的靜態(tài)手勢(shì)識(shí)別系統(tǒng),完成對(duì)預(yù)定義的6種靜態(tài)手勢(shì)的識(shí)別。論文首先討論了幾種常見(jiàn)的圖像預(yù)處理方法,以用來(lái)去除圖像的噪聲和增強(qiáng)圖像的質(zhì)量,并分別對(duì)梯度直方圖(HOG特征)和支持向量機(jī)(SVM)進(jìn)行了相關(guān)的介紹。由于手勢(shì)的多樣性以及圖像背景的復(fù)雜性,本文選擇單一特征最為強(qiáng)大的HOG特征。與其他特征相比,HOG特征對(duì)于手勢(shì)圖像的光線變化和小幅度旋轉(zhuǎn)方面有較強(qiáng)的魯棒性。將HOG特征與SVM結(jié)合起來(lái),作為手勢(shì)的識(shí)別算法。實(shí)驗(yàn)結(jié)果表明,HOG結(jié)合SVM的方法對(duì)手勢(shì)識(shí)別有較好的分類效果。在對(duì)手勢(shì)圖像分類訓(xùn)練時(shí),常用的HOG特征維數(shù)較高,包含大量的冗余信息,使得特征的提取算法較為復(fù)雜。為了克服這一不足,提出一種改進(jìn)算法,引入了主成分析法(PCA)對(duì)HOG特征進(jìn)行降維處理,形成PCA-HOG特征,并與LBP特征相融合形成新的PCA-HOG+LBP融合手勢(shì)特征。該融合特征既有手勢(shì)邊緣梯度信息,又有紋理特征信息,能有效彌補(bǔ)單一HOG特征的不足,提高手勢(shì)在遮擋情況下的識(shí)別率。最后用Jochen Triesch手勢(shì)庫(kù)中的手勢(shì)圖像對(duì)本文的識(shí)別算法進(jìn)行驗(yàn)證。結(jié)果表明,基于PCA-HOG+LBP特征的識(shí)別算法在提高手勢(shì)識(shí)別率的同時(shí)也能更好的保證實(shí)時(shí)性。最后,基于Microsoft Visual Studio 2010和Open CV環(huán)境搭建了手勢(shì)識(shí)別的原型系統(tǒng),設(shè)計(jì)并實(shí)現(xiàn)了一個(gè)小型手勢(shì)識(shí)別系統(tǒng)。論述了該系統(tǒng)流程,關(guān)鍵模塊的實(shí)現(xiàn)代碼等內(nèi)容,通過(guò)攝像頭采集手勢(shì)圖并自制手勢(shì)庫(kù)完成測(cè)試,實(shí)驗(yàn)結(jié)果表明證明改進(jìn)后的算法在本系統(tǒng)是具有可行性的。
[Abstract]:With the development of computer technology, more and more man-machine interaction methods appear. Gesture recognition has become an important human-computer interaction method (HCI). Because of the intuitive and natural features of gestures. But the diversity of gesture itself and the difference in time and space make gesture recognition a challenging interdisciplinary research topic. How to recognize the meaning of gestures quickly and accurately has become the focus of research. In this paper, a static gesture recognition system based on computer vision is designed and implemented with the aim of considering real-time and improving the recognition rate of gesture. The recognition of six predefined static gestures is accomplished. In this paper, several common image preprocessing methods are discussed to remove image noise and enhance image quality. Gradient histogram (HOG) and support vector machine (SVM) are introduced respectively. Due to the diversity of gestures and the complexity of image background, the single feature is chosen as the most powerful HOG feature in this paper. Compared with other features, HOG features are robust to light variation and small rotation of gesture images. HOG features are combined with SVM as gesture recognition algorithms. The experimental results show that the method of HOG combined with SVM has better classification effect for gesture recognition. In the training of gesture image classification, the commonly used HOG feature dimension is high and contains a lot of redundant information, which makes the feature extraction algorithm more complex. In order to overcome this shortcoming, an improved algorithm is proposed. The principal component analysis method (PCA) is introduced to reduce the dimension of HOG features to form PCA-HOG features, and to merge with LBP features to form new PCA-HOG LBP fusion gesture features. The fusion feature has both gradient information of gesture edge and texture feature information, which can effectively compensate for the deficiency of single HOG feature and improve the recognition rate of gesture in occlusion. Finally, the recognition algorithm of this paper is verified by the gesture image in Jochen Triesch gesture database. The results show that the recognition algorithm based on PCA-HOG LBP features not only improves the recognition rate of gestures, but also ensures better real-time performance. Finally, a prototype system of gesture recognition is built based on Microsoft Visual Studio 2010 and Open CV, and a small gesture recognition system is designed and implemented. The flow of the system and the code of the key module are discussed. The gesture diagram is collected by the camera and the hand gesture database is made to complete the test. The experimental results show that the improved algorithm is feasible in this system.
【學(xué)位授予單位】：蘭州理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳銳;王敏;陳肖;;基于PCA降維的HOG與LBP融合的行人檢測(cè)[J];信息技術(shù);2015年02期

2 魏志光;和青芳;;基于數(shù)學(xué)形態(tài)學(xué)車牌自動(dòng)定位和傾斜校正[J];北京聯(lián)合大學(xué)學(xué)報(bào);2014年02期

3 林水強(qiáng);吳亞?wèn)|;陳永輝;;基于幾何特征的手勢(shì)識(shí)別方法[J];計(jì)算機(jī)工程與設(shè)計(jì);2014年02期

4 汪成亮;周佳;黃晟;;基于高斯混合模型與PCA-HOG的快速運(yùn)動(dòng)人體檢測(cè)[J];計(jì)算機(jī)應(yīng)用研究;2012年06期

5 凌云明;;手勢(shì)識(shí)別在人機(jī)交互技術(shù)中的應(yīng)用[J];信息與電腦(理論版);2011年09期

6 王欣;;信息無(wú)障礙領(lǐng)域技術(shù)與產(chǎn)業(yè)發(fā)展現(xiàn)狀[J];信息技術(shù)與標(biāo)準(zhǔn)化;2011年04期

7 丁世飛;齊丙娟;譚紅艷;;支持向量機(jī)理論與算法研究綜述[J];電子科技大學(xué)學(xué)報(bào);2011年01期

8 曾春;李曉華;周激流;;基于感興趣區(qū)梯度方向直方圖的行人檢測(cè)[J];計(jì)算機(jī)工程;2009年24期

9 袁春蘭;熊宗龍;周雪花;彭小輝;;基于Sobel算子的圖像邊緣檢測(cè)研究[J];激光與紅外;2009年01期

10 朱穎,江澤濤;基于Sobel算子的亞像素邊緣檢測(cè)方法[J];南昌航空工業(yè)學(xué)院學(xué)報(bào)(自然科學(xué)版);2005年02期

相關(guān)會(huì)議論文 前1條

1 孫超;馮志全;李揚(yáng);張明敏;張文杰;潘志庚;;基于手勢(shì)識(shí)別的人機(jī)交互綜述[A];第六屆和諧人機(jī)環(huán)境聯(lián)合學(xué)術(shù)會(huì)議（HHME2010)、第19屆全國(guó)多媒體學(xué)術(shù)會(huì)議（NCMT2010）、第6屆全國(guó)人機(jī)交互學(xué)術(shù)會(huì)議（CHCI2010）、第5屆全國(guó)普適計(jì)算學(xué)術(shù)會(huì)議（PCC2010）論文集[C];2010年

相關(guān)碩士學(xué)位論文 前10條

1 李亞蘭;基于視覺(jué)的實(shí)時(shí)靜態(tài)手勢(shì)識(shí)別技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2015年

2 g罘，

本文編號(hào)：2360765